xinformatics

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

flower

Flower: A Friendly Federated Learning Framework

maturin

Build and publish crates with pyo3, cffi and uniffi bindings as well as rust binaries as python packages

awesome-jupyterlab

A curated list of awesome JupyterLab extensions and resources

conversational-datasets

Large datasets for conversational AI

duckdb-wasm

WebAssembly version of DuckDB

llm-app-stack

PyHealth

A Deep Learning Python Toolkit for Healthcare Applications.

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

ringattention

Transformers with Arbitrarily Large Context

GML2023

Graph Machine Learning course, Xavier Bresson, 2023

Awesome-Scientific-Language-Models

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery

Federated-Learning-in-PyTorch

Handy PyTorch implementation of Federated Learning (for your painless research)

how_attentive_are_gats

Code for the paper "How Attentive are Graph Attention Networks?" (ICLR'2022)

spacetime

Code for SpaceTime 🌌⏱️. Proposed in Effectively Modeling Time Series with Simple Discrete State Spaces, ICLR 2023.

Time2Graph

Source codes for Time2Graph model.

openemr-devops

OpenEMR administration and deployment tooling

STTN

The official code for "Spatial temporal transformer networks for traffic flow forecasting"

MongoDB_PyMongo_Tutorial

Introduction to MongoDB and tutorial to implement in Python using PyMongo

Time2GraphPlus

Source codes for Time2Graph+ model.

alphafold

Open source code for AlphaFold to extract protein embeddings

TransformEHR

recurrence-with-self-attention

The repository contains source code and data from the paper titled "Recurrence and Self-Attention vs the Transformer for Time-Series Classification: A Comparative Study".

matryoshka-representation-learning

PyTorch implementation for MRL

TransDTI

TransDTI: Transformer-based language models for estimating DTIs and building a drug-recommendation workflow

python-cassandra-intro

NeXtQSM

A complete deep learning pipeline for data-consistent quantitative susceptibility mapping trained with hybrid data

datasceyence

My journey of applying deep learning to ophthalmology using Python.